第四章 服务器基础知识.ppt

服务器芯片组家族—英特尔 但2006年，英特尔在质疑与期待中，推出了全新的Bensley服务器平台和38年来最重要的产品——基于全新酷睿微处理器体系架构的至强5100系列（代号Woodcrest）。英特尔平台化策略的成功推出和新一代微体系架构的转换，让业界开始重拾对英特尔的信心。酷睿至强处理器凭借低功耗64位双核处理器、硬件辅助虚拟化（VT）、全新的双独立点对点总线、全缓冲DDR2 DIMM内存（FBD）、英特尔I/O加速技术、嵌入式RAID技术、全新酷睿微体系结构、四核支持等一连串的崭新特性，打响了从对手口中夺食的战略大反攻。 英特尔CPU产品家族 服务器的部件技术—内存技术发展史 Intel推动的Rambus DRAM内存，基于一种类RISC(Reduced Instruction Set Computing，精简指令集计算机)理论，理论上可以减少数据的复杂性，使得整个系统性能得到提高 DDR SDRAM (Dual Date Rate SDRAM)简称DDR，也就是“双倍速率SDRAM“的意思。DDR可以说是SDRAM的升级版本， DDR在时钟信号上升沿与下降沿各传输一次数据，这使得DDR的数据传输速度为传统SDRAM的两倍。 DDR2 能够在100MHz 的发信频率基础上提供每插脚最少400MB/s 的带宽，发热量进一步降低，此外，DDR2 将融入CAS、OCD、ODT 等新性能指标和中断指令，提升内存带宽的利用率 提问：解释X3200 M3 ,Xeon 4C X3460 2.8GHz/1333MHz Primary difference between the two implementations (at this level) are: The Intel processor has a smaller L1 but larger L2 caches. Shared L2 cache vs. separate Shared cache allows a larger cache to be available to one core if it needs it (and assumes the other core does not need it). This is dynamic allocation of the cache resource. 3. Integrated memory controller vs. non-integrated The presence of the System Request Interface, Cross bar, and the high-speed serial interface (HyperTransport) are all logical results of having an integrated memory controller It is difficult to say which implementation/system architecture is better. They simply are a different means to the end. What matters is how they perform on a given workload. Intel Turbo Boost Technology increases performance of both multi-threaded and single threaded workloads. Intel Turbo Boost Technology is activated when the Operating System (OS) requests the highest processor performance state (P0). The maximum frequency of Intel? Turbo Boost Technology is dependent on the number of active cores. The amount of time the processor spends in the Intel Turbo Boost Technology state depends on the workload and operating environment, providing the performance you need, when and where you need it. Any of the following can set the upper limit of Intel Tu